Composite Kernels for Fusing Colour Information in Face Verification Systems

In this work, a novel method of fusing colour information in feature level is proposed considering a face verification system. For this purpose, composite kernels which have been already used in support vector machine classifier is applied within the framework of the generalised discriminant analysis (GDA) algorithm. The performance of the resulting system is evaluated using the XM2VTS face database and its associated experimental protocols. Our experiments show that by combining colour information using the proposed approach the good classification performance demonstrated by the kernel based methods can be further improved.